Gemma on NVIDIA Ada
Can I run Gemma 3 27B on an RTX 4060 Ti 16GB?
Not at Q4_K_M — it needs 17.5 GB against 14.2 GB available. Drop to IQ3_M and it fits, at about 13.4 tokens per second.
Won't fit
17.5 GB of 14.2 GB · 123%018 GB
Weights
15.6 GB
KV cache
1.1 GB
Runtime overhead
0.8 GB
Over the limit
3.3 GB
Short by 3.3 GB. You can run it with 48 of 62 layers on the RTX 4060 Ti 16GB and the rest in system RAM, at roughly 5.89 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation5.89tok/s
Prompt processing337tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of Gemma 3 27B on a RTX 4060 Ti 16GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 51.0 GB | 53.0 GB | Won't fit | — | 0.90 |
| INT8 / W8A8 | 8.50 | 26.8 GB | 28.7 GB | Won't fit | — | 2.14 |
| Q8_0 (GGUF) | 8.50 | 26.8 GB | 28.7 GB | Won't fit | — | 2.14 |
| FP8 (E4M3) | 8.00 | 25.5 GB | 27.4 GB | Won't fit | — | 2.29 |
| Q6_K | 6.56 | 20.9 GB | 22.9 GB | Won't fit | — | 3.22 |
| Q5_K_M | 5.67 | 18.1 GB | 20.0 GB | Won't fit | — | 4.29 |
| Q5_K_S | 5.52 | 17.6 GB | 19.5 GB | Won't fit | — | 4.53 |
| Q4_K_M | 4.85 | 15.6 GB | 17.5 GB | Won't fit | — | 5.89 |
| AWQ 4-bit | 4.25 | 15.5 GB | 17.4 GB | Won't fit | — | 6.12 |
| GPTQ 4-bit | 4.25 | 15.5 GB | 17.4 GB | Won't fit | — | 6.12 |
| MXFP4 | 4.25 | 15.5 GB | 17.4 GB | Won't fit | — | 6.12 |
| Q4_K_S | 4.58 | 14.8 GB | 16.7 GB | Won't fit | — | 6.85 |
| Q4_0 | 4.55 | 14.7 GB | 16.6 GB | Won't fit | — | 7.13 |
| IQ4_XS | 4.25 | 13.8 GB | 15.7 GB | Won't fit | — | 8.50 |
| Q3_K_M | 3.91 | 12.7 GB | 14.7 GB | Won't fit | 3K | 10.9 |
| IQ3_M | 3.70 | 12.1 GB | 14.0 GB | Fits, but tight | 10K | 13.4 |
| IQ3_XXS | 3.06 | 10.2 GB | 12.1 GB | Runs comfortably | 33K | 15.7 |
| Q2_K | 2.63 | 8.9 GB | 10.8 GB | Runs comfortably | 48K | 17.9 |
| IQ2_XXS | 2.06 | 7.1 GB | 9.1 GB | Runs comfortably | 68K | 21.7 |
| IQ1_M | 1.75 | 6.2 GB | 8.1 GB | Runs comfortably | 79K | 24.7 |